Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/michabirklbauer/hgb_dse_text_mining
Contents for the practical part of the lecture Text Mining
https://github.com/michabirklbauer/hgb_dse_text_mining
deep-learning educational how-to keras machine-learning nlp python spacy tensorflow text-classification text-clustering text-mining
Last synced: about 2 months ago
JSON representation
Contents for the practical part of the lecture Text Mining
- Host: GitHub
- URL: https://github.com/michabirklbauer/hgb_dse_text_mining
- Owner: michabirklbauer
- License: mit
- Created: 2022-11-14T21:17:25.000Z (about 2 years ago)
- Default Branch: master
- Last Pushed: 2024-11-07T08:24:47.000Z (about 2 months ago)
- Last Synced: 2024-11-07T08:27:00.960Z (about 2 months ago)
- Topics: deep-learning, educational, how-to, keras, machine-learning, nlp, python, spacy, tensorflow, text-classification, text-clustering, text-mining
- Language: Jupyter Notebook
- Homepage:
- Size: 59.8 MB
- Stars: 0
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Introduction to Natural Language Processing
Contents for the practical part of the lecture Text Mining @ FH Hagenberg.
## Requirements
Language:
- [Python 3.12](https://www.python.org/downloads/)
If you want to run the notebooks locally please install the requirements noted in `requirements.txt`:
- `pip install -r requirements.txt`
For chapters 5 and 6 you will additionally need `tensorflow` and `transformers`:
- `pip install tensorflow transformers`
## Chapters
- Chapter 1: spaCy -> [open in Google Colab](https://colab.research.google.com/github/michabirklbauer/hgb_dse_text_mining/blob/master/spaCy.ipynb)
- Chapter 2: NLTK and Gensim -> [open in Google Colab](https://colab.research.google.com/github/michabirklbauer/hgb_dse_text_mining/blob/master/NLTK_Gensim.ipynb)
- Chapter 3: Clustering -> [open in Google Colab](https://colab.research.google.com/github/michabirklbauer/hgb_dse_text_mining/blob/master/Features_Clustering.ipynb)
- Chapter 4: Classification -> [open in Google Colab](https://colab.research.google.com/github/michabirklbauer/hgb_dse_text_mining/blob/master/Classification.ipynb)
- Chapter 4.1: RF Classification -> [open in RStudio Cloud](https://rstudio.cloud/content/4961423)
- Chapter 5: Sentiment Analysis -> [open in Google Colab](https://colab.research.google.com/github/michabirklbauer/hgb_dse_text_mining/blob/master/Sentiment.ipynb)
- Chapter 6: Image Captioning -> [open in Google Colab](https://colab.research.google.com/github/michabirklbauer/hgb_dse_text_mining/blob/master/Captioning.ipynb)
Solutions for the exercises will be available at [michabirklbauer/hgb_dse_text_mining_solutions](https://github.com/michabirklbauer/hgb_dse_text_mining_solutions) *after* the lectures.
## References
- A lot of the neural net slides is taken from [DeepMind's 2020 Deep Learning Lecture Series](https://www.youtube.com/playlist?list=PLqYmG7hTraZCDxZ44o4p3N5Anz3lLRVZF).
- Chapter 5 is an adaptation of [Google Developers' Machine Learning Foundations](https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Lesson%202.ipynb).
- Chapter 6 is an adaptation of the official [Keras image captioning example](https://keras.io/examples/vision/image_captioning/).
## Contact
- [[email protected]](mailto:[email protected])
- [[email protected]](mailto:[email protected])